Skip to content

armgit / laya

Public Imported from GitHub
0

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

docs(confidence): note option-count sensitivity

Humaira Ambreen6c895fcc8bbe
diff --git a/README.md b/README.md
index 0560d3e6..0ed494b2 100644
--- a/README.md
+++ b/README.md
@@ -453,7 +453,7 @@ Three things differ from Jev when you port a client:
* **Options per question.** A question's options share the checkpoint's option budget, `head_max_len` (192 tokens on `laya`, 256 on the other two), not Jev's cap of 255 options. Once they overflow it, around 20 options with a short description each, every option is trimmed to fit, so long or similar labels can reach the model reading the same ([Where Jev leads](#where-jev-leads)). Once they no longer fit the window at all, the request is rejected with 422. With short labels such as `Queue 042: Tickets routed to queue 42` that happens above 126 options on `laya` and 254 on the other two; the exact point moves with the length of the instructions and labels. For more candidates, narrow them first with `predict_shortlist` ([Honest limits](#honest-limits)).
* **Score levels.** Every level needs a description. A `null` level is rejected with 422 rather than scored and echoed back in `legend`.
-* **`confidence`** on `choice` and `score` answers is 1 minus normalised entropy, a measure of how concentrated the distribution is, not Jev's `(n·p_max − 1)/(n − 1)`. A threshold carried over from Jev does not transfer. For one calibrated number on every question type, gate on `answer_confidence`, the probability of the reported answer.
+* **`confidence`** on `choice` and `score` answers is 1 minus normalised entropy, a measure of how concentrated the distribution is, not Jev's `(n·p_max − 1)/(n − 1)`. A threshold carried over from Jev does not transfer. Its value can also shift with the number of options, so validate any cutoff at the counts your workload uses. For one calibrated number on every question type, gate on `answer_confidence`, the probability of the reported answer.
### Nix / NixOS